pith. sign in

arxiv: 2606.04338 · v1 · pith:DJH7PWM7new · submitted 2026-06-03 · 💻 cs.LG · cs.CR

Federated Learning for Multi-Center Sepsis Early Prediction with Privacy-Preserving

Xixi Tian , Di Wu , Xiang Liu , Yiziting Zhu , Yujie Li , Xin Shu , Bin Yi This is my paper

Pith reviewed 2026-06-28 07:11 UTC · model grok-4.3

classification 💻 cs.LG cs.CR
keywords federated learningsepsis predictionprivacy preservationmulti-center medical datamachine learningclinical early warning
0
0 comments X

The pith

Federated learning matches centralized sepsis prediction accuracy while keeping patient data local to each hospital.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper examines whether federated learning can enable accurate early sepsis prediction across multiple hospitals without centralizing raw patient records. Using 648 samples from three Chinese hospitals, it trains both a centralized baseline model and a horizontal federated model, then compares their performance. Results show the federated version reaches nearly identical prediction accuracy. Additional analysis of the exchanged model parameters indicates that attackers cannot recover the original patient data from them. This demonstrates a workable path for privacy-preserving collaboration on clinical prediction tasks.

Core claim

The federated learning-based model achieves highly comparable prediction accuracy to the centralized counterpart, while fundamentally avoiding privacy leakage. Further privacy security analysis verifies that malicious attackers cannot reconstruct the original patient data from the transmitted model parameters, indicating strong resistance against data reconstruction attacks.

What carries the argument

Horizontal federated learning framework that trains a shared sepsis prediction model by exchanging only model parameters across three hospital datasets.

Load-bearing premise

The privacy security analysis performed on the transmitted model parameters is sufficient to demonstrate resistance against data reconstruction attacks in a real deployment setting.

What would settle it

An experiment in which an attacker reconstructs identifiable patient records from the exchanged model parameters alone would disprove the privacy preservation claim.

Figures

Figures reproduced from arXiv: 2606.04338 by Bin Yi, Di Wu, Xiang Liu, Xin Shu, Xixi Tian, Yiziting Zhu, Yujie Li.

Figure 1
Figure 1. Figure 1: Federated Learning Framework for Sepsis Prediction [PITH_FULL_IMAGE:figures/full_fig_p003_1.png] view at source ↗
read the original abstract

Privacy-sensitive and distributed characteristics of multi-center medical data bring severe obstacles to centralized modeling for accurate early prediction of sepsis. Federated learning (FL) has attracted growing attention as a promising framework for collaborative model development, as it allows multiple institutions to jointly train predictive models without directly sharing or centralizing raw data. Nevertheless, its practical performance, robustness, and privacy-preserving benefits remain insufficiently evaluated using real-world clinical datasets. To bridge this gap, this study systematically examines the application of federated learning to multi-center sepsis prediction. The experimental dataset consists of 648 clinically screened samples collected from three tertiary hospitals in China, with rigorous inclusion and exclusion criteria. We establish a centralized training paradigm as the performance baseline, and then implement a horizontal federated learning framework for distributed collaborative modeling. Extensive experimental results demonstrate that the federated learning-based model achieves highly comparable prediction accuracy to the centralized counterpart, while fundamentally avoiding privacy leakage. Further privacy security analysis verifies that malicious attackers cannot reconstruct the original patient data from the transmitted model parameters, indicating strong resistance against data reconstruction attacks. This work not only validates the practicality and security of federated learning in clinical sepsis prediction, but also provides a reliable and feasible solution for privacy-preserving multi-center medical collaboration.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 1 minor

Summary. The paper applies horizontal federated learning (FL) to early sepsis prediction using 648 samples from three Chinese hospitals. It compares an FL model against a centralized baseline, claiming highly comparable predictive accuracy while avoiding privacy leakage, with a privacy security analysis asserted to show that transmitted model parameters resist reconstruction by malicious attackers.

Significance. If the empirical results and privacy analysis hold with adequate detail, the work would supply a concrete real-world validation of FL for privacy-sensitive multi-center clinical prediction on modest per-site data volumes, offering a practical template for healthcare institutions reluctant to share raw records.

major comments (2)
  1. [Abstract] Abstract (final paragraph): the claim that 'malicious attackers cannot reconstruct the original patient data from the transmitted model parameters' via 'privacy security analysis' supplies no threat model (honest-but-curious server, malicious client, etc.), no attack method (gradient inversion, model inversion, membership inference), and no quantitative leakage metric. This directly underpins the 'fundamentally avoiding privacy leakage' half of the central claim and cannot be assessed without those elements.
  2. [Abstract] Abstract: the statement that the FL model 'achieves highly comparable prediction accuracy to the centralized counterpart' is presented without any performance numbers, AUC/accuracy values, confidence intervals, or statistical tests, preventing verification of the main empirical result.
minor comments (1)
  1. [Abstract] The dataset description mentions 'rigorous inclusion and exclusion criteria' but provides none; adding them would improve reproducibility.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive comments on the abstract. We address each major comment below and will revise the abstract accordingly to improve self-containment and verifiability.

read point-by-point responses

  1. Referee: [Abstract] Abstract (final paragraph): the claim that 'malicious attackers cannot reconstruct the original patient data from the transmitted model parameters' via 'privacy security analysis' supplies no threat model (honest-but-curious server, malicious client, etc.), no attack method (gradient inversion, model inversion, membership inference), and no quantitative leakage metric. This directly underpins the 'fundamentally avoiding privacy leakage' half of the central claim and cannot be assessed without those elements.

    Authors: We agree that the abstract would benefit from additional detail on the privacy analysis to allow independent assessment. The full manuscript includes a dedicated privacy security analysis specifying the threat model and evaluating reconstruction attacks with quantitative metrics. We will revise the abstract to concisely note the threat model (honest-but-curious server), the attack method (gradient inversion), and key quantitative findings on reconstruction resistance. revision: yes

  2. Referee: [Abstract] Abstract: the statement that the FL model 'achieves highly comparable prediction accuracy to the centralized counterpart' is presented without any performance numbers, AUC/accuracy values, confidence intervals, or statistical tests, preventing verification of the main empirical result.

    Authors: We agree that the abstract should report specific performance metrics for transparency. The manuscript's experimental results section contains the AUC, accuracy, and related metrics for the federated and centralized models, including comparisons. We will revise the abstract to include these key values and indicate the observed comparability. revision: yes

Circularity Check

0 steps flagged

No circularity: empirical comparison with independent experimental results

full rationale

The paper reports an empirical study comparing centralized and federated learning models on a fixed 648-patient dataset from three hospitals. Performance claims rest on direct accuracy metrics from training runs, and the privacy claim rests on a separate security analysis of transmitted parameters. No equations, fitted parameters, or predictions are defined in terms of the target quantities, and no load-bearing self-citations or uniqueness theorems are invoked. The central claims therefore do not reduce to their inputs by construction.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

The central claim rests on standard assumptions of horizontal federated learning and on the representativeness of the screened 648-sample dataset from three hospitals; no free parameters, invented entities, or non-standard axioms are explicitly introduced in the abstract.

axioms (1)
  • domain assumption Horizontal federated learning can be applied directly to the screened multi-center clinical dataset without prohibitive heterogeneity effects
    Invoked by the experimental design that compares centralized and federated training on the same 648 samples.

pith-pipeline@v0.9.1-grok · 5762 in / 1040 out tokens · 23024 ms · 2026-06-28T07:11:56.253347+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

76 extracted references

  1. [1]

    ”Optimizing neural disorder treatment through federated learning and multi-institutional data collaboration.” Federated Learning for Neural Disorders in Healthcare 6.0 (2025): 120

    Puttanapura, Jagadeshwari, and Srinath Doss. ”Optimizing neural disorder treatment through federated learning and multi-institutional data collaboration.” Federated Learning for Neural Disorders in Healthcare 6.0 (2025): 120

    2025

  2. [2]

    Di Wu, Shihui Li, Yi He, Xin Luo, and Xinbo Gao, Non-Gradient Hash Factor Learning for High-Dimensional and Incomplete Data Representation Learning, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 48, no. 5, pp. 5811-5826, May 2026

    2026

  3. [3]

    ‘Enhancing Privacy in Federated Learning: Mitigating Model Inversion Attacks through Selective Model Transmission and Algorithmic Improvements.’ (2024)

    Jonsson, Isak. ‘Enhancing Privacy in Federated Learning: Mitigating Model Inversion Attacks through Selective Model Transmission and Algorithmic Improvements.’ (2024)

    2024

  4. [4]

    Concept Factorization via Self-Representation and Adaptive Graph Structure Learning

    Yang Z, Wu D, Chen J, Luo X. Concept Factorization via Self-Representation and Adaptive Graph Structure Learning. In2025 International Joint Conference on Neural Networks (IJCNN) 2025 Jun 30 (pp. 1-8). IEEE

    2025

  5. [5]

    Di Wu, Zetong Tang, Yi He, and Xin Luo, SchemaRAG: A Schema-aware Retrieval-Augmented Generation Framework for Text-to-SQL. Proc. ACM Manag. Data 4, 1 (SIGMOD), Article 82 (February 2026), 26 pages, 2026

    2026

  6. [6]

    Luo, Xin, et al. ”A novel multi-agent reinforcement learning framework for robust exception handling of manufacturing service collaboration based on asymmetric information.” Journal of Manufacturing Systems 79 (2025): 364-382

    2025

  7. [7]

    Rajendran, Suraj, et al. ‘Data heterogeneity in federated learning with Electronic Health Records: Case studies of risk prediction for acute kidney injury and sepsis diseases in critical care.’ PLOS Digital Health 2.3 (2023): e0000117

    2023

  8. [8]

    Di Wu, Shuai Zhong, Yi He, Xin Luo, and Xinbo Gao, Federated Latent Factorization of Tensors for Privacy-Preserving Representation Learning to Large-scale Dynamic Weighted Directed Network, IEEE Transactions on Dependable and Secure Computing, 2026

    2026

  9. [9]

    Naveen, and A

    Priyanka, K., R. Naveen, and A. Zoya. ”Federated Learning Frameworks for Privacy-Preserving Diagnostic Imaging in Multi-Site Hospital Clusters.” International Journal of Advanced Multidisciplinary Application 3.3 (2026): 14-19

    2026

  10. [10]

    Di Wu, Cheng Liang, Yi He, Yan Qiao, and Xin Luo, ”Multimetric Autoencoder for Representing High-Dimensional and Incomplete Data,” IEEE Transactions on Systems Man Cybernetics-Systems, vol. 56, no. 3, pp. 1533-1546, March 2026

    2026

  11. [11]

    Uzzaman, Arfan. ”Federated Learning–Driven Real-Time Disease Surveillance For Smart Hospitals Using Multi-Source Heterogeneous Healthcare Data.” ASRC Procedia: Global Perspectives in Science and Scholarship 1.01 (2025): 1390-1423

    2025

  12. [12]

    ”Federated Latent Factor Learning for Privacy-Preserving Spatio-Temporal Signal Recovery.” In Proceedings of the ACM Web Conference 2026, pp

    Yu, Chengjun, Di Wu, Yi He, Jia Chen, and Xin Luo. ”Federated Latent Factor Learning for Privacy-Preserving Spatio-Temporal Signal Recovery.” In Proceedings of the ACM Web Conference 2026, pp. 2905-2916. 2026

    2026

  13. [13]

    ‘Privacy-Preserving Lightweight Federated Learning Framework for Sepsis Prediction.’ Computing Proceedings 1 (2025)

    Pallewela, Lahiruni Chamudika Kumari. ‘Privacy-Preserving Lightweight Federated Learning Framework for Sepsis Prediction.’ Computing Proceedings 1 (2025)

    2025

  14. [14]

    Uzzaman, Arfan. ‘Federated Learning–Driven Real-Time Disease Surveillance For Smart Hospitals Using Multi-Source Heterogeneous Healthcare Data.’ ASRC Procedia: Global Perspectives in Science and Scholarship 1, no. 01 (2025): 1390-1423

    2025

  15. [15]

    ”A Robust Approach to Electricity Theft Detection via Tensor Representation-Driven Contrastive Distillation.” IEEE Transactions on Industrial Informatics (2026)

    Qin, Wen, Yuting Ding, and Xin Luo. ”A Robust Approach to Electricity Theft Detection via Tensor Representation-Driven Contrastive Distillation.” IEEE Transactions on Industrial Informatics (2026)

    2026

  16. [16]

    ”Federated Learning for Privacy-Preserving Healthcare Data Analytics.” Peer-Reviewed Journal of Computer Science (PRJCS) 1.3 (2026): 20-26

    Jayasurya, Manasy. ”Federated Learning for Privacy-Preserving Healthcare Data Analytics.” Peer-Reviewed Journal of Computer Science (PRJCS) 1.3 (2026): 20-26

    2026

  17. [17]

    ”Modularized Graph Convolutional Network.” IEEE/CAA Journal of Automatica Sinica 13, no

    He, Tiantian, Zhixuan Duan, and Xin Luo. ”Modularized Graph Convolutional Network.” IEEE/CAA Journal of Automatica Sinica 13, no. 3 (2026): 737-739

    2026

  18. [18]

    ‘Scalable Autoencoder-Based Liver Disease Identification in Cloud-Integrated Healthcare Systems.’ Int

    Mekala, R. ‘Scalable Autoencoder-Based Liver Disease Identification in Cloud-Integrated Healthcare Systems.’ Int. J. of Multidisciplinary and Current research 12 (2024)

    2024

  19. [19]

    A survey of latent factorization of tensor-based model compression: Algorithms, toolboxes and future directions

    He Y , Wu H, Liu W, Luo X. A survey of latent factorization of tensor-based model compression: Algorithms, toolboxes and future directions. Neurocomputing. 2026 Mar 25:133455

    2026

  20. [20]

    ”Advanced High-Order Graph Convolutional Networks With Assorted Time-Frequency Transforms.” IEEE/CAA Journal of Automatica Sinica 13.2 (2026): 394-408

    Wang, Ling, Ye Yuan, and Xin Luo. ”Advanced High-Order Graph Convolutional Networks With Assorted Time-Frequency Transforms.” IEEE/CAA Journal of Automatica Sinica 13.2 (2026): 394-408

    2026

  21. [21]

    ‘Federated Learning for Cardiovascular Disease Prediction: A Comparative Review of Biosignal-and EHR-Based Approaches.’ Healthcare

    Ryu, Hagyeong, et al. ‘Federated Learning for Cardiovascular Disease Prediction: A Comparative Review of Biosignal-and EHR-Based Approaches.’ Healthcare. V ol. 13. No. 21. MDPI, 2025

    2025

  22. [22]

    TraceHG: An Unsupervised Dual-View Framework for Microservice Anomaly Detection

    Han N, Lu S, Lin Z, Li B, Wang N, Luo X. TraceHG: An Unsupervised Dual-View Framework for Microservice Anomaly Detection. IEEE Transactions on Services Computing. 2026 Feb 24

    2026

  23. [23]

    and Luo, X., 2026

    Wu, D., Liang, C., He, Y ., Qiao, Y . and Luo, X., 2026. Multimetric Autoencoder for Representing High-Dimensional and Incomplete Data. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 56(3), pp.1533-1546

    2026

  24. [24]

    A novel magnetite ore refined sorting method based on magnetic induction and CNN-SK-BiLSTM network

    ZEnG D, PAn C, FEnG KA, Luo X. A novel magnetite ore refined sorting method based on magnetic induction and CNN-SK-BiLSTM network. Gospodarka Surowcami Mineralnymi. 2025;41

    2025

  25. [25]

    and Luo, X., 2026

    Li, Z., Hu, P., Deng, X., Hu, L., Li, S. and Luo, X., 2026. A Novel L 1-and-L 2-Norm-Integrated Parameter Identification Model for Robot Calibration. IEEE Transactions on Industrial Electronics

    2026

  26. [26]

    ”Secure Multi-Organization Healthcare Data Analysis Using Federated AI Architectures.” American Data Science Journal for Advanced Computations (ADSJAC) 4.01 (2026)

    Valiki, Dileep Valiki Dileep. ”Secure Multi-Organization Healthcare Data Analysis Using Federated AI Architectures.” American Data Science Journal for Advanced Computations (ADSJAC) 4.01 (2026)

    2026

  27. [27]

    ”Graph Tensor Convolutional Network.” IEEE Transactions on Systems, Man, and Cybernetics: Systems (2026)

    Wang, Ling, Ye Yuan, and Xin Luo. ”Graph Tensor Convolutional Network.” IEEE Transactions on Systems, Man, and Cybernetics: Systems (2026)

    2026

  28. [28]

    JANKAR, Dipali, and Sanjay L. BADJATE. ”Federated Learning and Collaborative AI Models in Neuroscience Research.” AI-driven Healthcare Innovations: Applications in Neurology and Medicine (2026): 261-277

    2026

  29. [29]

    Valiki, Dileep. ”Federated AI Architectures for Secure Multi-Organization Healthcare Data Analysis.” International Journal of Computer Technology and Electronics Communication 8.6 (2025): 11858-11871

    2025

  30. [30]

    Tensor Low-Rank Orthogonal Compression for Convolutional Neural Networks

    He Y , Luo X. Tensor Low-Rank Orthogonal Compression for Convolutional Neural Networks. IEEE/CAA Journal of Automatica Sinica. 2026 Jan 30;13(1):227-9

    2026

  31. [31]

    Non-Gradient Hash Factor Learning for High-Dimensional and Incomplete Data Representation Learning

    Wu D, Li S, He Y , Luo X, Gao X. Non-Gradient Hash Factor Learning for High-Dimensional and Incomplete Data Representation Learning. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2026 Jan 16. 53, (2), pp. 753–764

    2026

  32. [32]

    ”Federated Multi-Modal Learning for Privacy Preserving Healthcare AI.” (2026)

    Grace, Abigail. ”Federated Multi-Modal Learning for Privacy Preserving Healthcare AI.” (2026)

    2026

  33. [33]

    ”End-to-end Graph Learning Approach for Cognitive Diagnosis of Student Tutorial.” arXiv preprint arXiv:2411.00845 (2024)

    Yang, Fulai, et al. ”End-to-end Graph Learning Approach for Cognitive Diagnosis of Student Tutorial.” arXiv preprint arXiv:2411.00845 (2024)

    arXiv 2024

  34. [34]

    ”A Federated Learning and Explainable AI Framework for Privacy-Preserving Brain Tumor Diagnosis Using Multi-Institutional MRI Data.” IEEE Access (2026)

    Gupta, Shubham, et al. ”A Federated Learning and Explainable AI Framework for Privacy-Preserving Brain Tumor Diagnosis Using Multi-Institutional MRI Data.” IEEE Access (2026)

    2026

  35. [35]

    ”Federated Learning in Biomedical and Health Informatics: A Systematic Review and Future Directions.” (2026)

    Hornback, Andrew, et al. ”Federated Learning in Biomedical and Health Informatics: A Systematic Review and Future Directions.” (2026)

    2026

  36. [37]

    Mini-Hes: A Parallelizable Second-order Latent Factor Analysis Model

    Wang J, Li W, Zhong Y , Luo X. Mini-Hes: A Parallelizable Second-order Latent Factor Analysis Model. arXiv preprint arXiv:2402.11948. 2024 Feb 19

    arXiv 2024

  37. [38]

    ”Adaptive Tucker Decomposition-based Progressive Model Compression for Convolutional Neural Networks.” Expert Systems with Applications (2026): 131153

    He, Yaping, Hao Wu, and Xin Luo. ”Adaptive Tucker Decomposition-based Progressive Model Compression for Convolutional Neural Networks.” Expert Systems with Applications (2026): 131153

    2026

  38. [39]

    CM-CGNS: Cross-Modal Clustering-Guided Negative Sampling for Self-Supervised Joint Learning from Medical Images and Reports

    Lan L, Li H, Xia Z, Zhou J, Zhu X, Li Y , Zhang Y , Luo X. CM-CGNS: Cross-Modal Clustering-Guided Negative Sampling for Self-Supervised Joint Learning from Medical Images and Reports. Available at SSRN 6110595. 2026

    2026

  39. [40]

    Rajput, Kanchan G., et al. ”The Convergence of Federated Learning for the Digital Healthcare Market: An Overview.” The Convergence of Federated Learning and Healthcare 5.0 and Beyond: A New Era of Intelligent Health Systems (2026): 161

    2026

  40. [41]

    Advancing Healthcare with Large Language Models: Techniques and Application

    Hu Z, Peng Z, Bi Z, Shen Q, Liu Z, Lou J, Luo X. Advancing Healthcare with Large Language Models: Techniques and Application. IEEE/CAA Journal of Automatica Sinica. 2025 Dec 31;12(12):2371-98

    2025

  41. [42]

    ”Model centric collaboration reduces data sharing barriers in medical artificial intelligence.” Discover Artificial Intelligence (2026)

    Dai, Yanan, et al. ”Model centric collaboration reduces data sharing barriers in medical artificial intelligence.” Discover Artificial Intelligence (2026)

    2026

  42. [43]

    ”Federated Learning in Privacy Preservation and Security Enhancement for e-Healthcare Systems.” AI in Smart and Secure Healthcare: Research Trends and Future Opportunities

    Baidya, Arkadeep, et al. ”Federated Learning in Privacy Preservation and Security Enhancement for e-Healthcare Systems.” AI in Smart and Secure Healthcare: Research Trends and Future Opportunities. Cham: Springer Nature Switzerland, 2026. 329-360

    2026

  43. [44]

    An adaptive recognition method for reliable collaboration of manufacturing services based on edge-aggregated graph convolutional network

    Liu Z, Zhang Z, Luo X, Pan C, Wang L, Tang H, He L. An adaptive recognition method for reliable collaboration of manufacturing services based on edge-aggregated graph convolutional network. International Journal of Production Research. 2025 Dec 20:1-28

    2025

  44. [45]

    A Sampling-Neighborhood-Regularized Latent Factorization of Tensor for Dynamic QoS Estimation

    Xu X, Lin M, Xu Z, Luo X. A Sampling-Neighborhood-Regularized Latent Factorization of Tensor for Dynamic QoS Estimation. IEEE Transactions on Network and Service Management. 2025 Dec 19;23:1707-22

    2025

  45. [46]

    Zhang, Zhen, et al. ”Reliable Collaboration Chain Mining for Workshop Manufacturing Services Based on Non-Local Graph Convolutional Networks.” 2023 7th International Conference on Electrical, Mechanical and Computer Engineering (ICEMCE). IEEE, 2023

    2023

  46. [47]

    Multi-Indicator Latent Factorization of Tensors for Spatio-Temporal Signal Recovery

    Yu C, Wu D, Chen J, Zhou M, Luo X. Multi-Indicator Latent Factorization of Tensors for Spatio-Temporal Signal Recovery. In2025 IEEE 31th International Conference on Parallel and Distributed Systems (ICPADS) 2025 Dec 14 (pp. 1-8). IEEE

    2025

  47. [49]

    ”Adaptive homomorphic federated learning framework for multi-institutional medical imaging with optimized diagnostic accuracy.” Scientific Reports (2026)

    Josephine Usha, L., et al. ”Adaptive homomorphic federated learning framework for multi-institutional medical imaging with optimized diagnostic accuracy.” Scientific Reports (2026)

    2026

  48. [50]

    Genetic Algorithm-Based Two-Step Optimization for Precise Latent Factor Analysis

    Lyu C, Cheng J, Luo X, Shi Y . Genetic Algorithm-Based Two-Step Optimization for Precise Latent Factor Analysis. IEEE Transactions on Neural Networks and Learning Systems. 2025 Nov 25

    2025

  49. [51]

    Soltanieh, Sahar, Farzad Khalvati, and E. Ann Yeh. ”Federated Learning in Neurology: Bridging Data Privacy and Artificial Intelligence for Brain Health.” Seminars in Neurology. Thieme Medical Publishers, Inc., 2025

    2025

  50. [52]

    Baghel, Randhir Singh, and Udit Mamodiya. ”Future Trends in Federated Learning: Enabling Secure and Personalized Healthcare Solutions.” The Convergence of Federated Learning and Healthcare 5.0 and Beyond: A New Era of Intelligent Health Systems. Cham: Springer Nature Switzerland,

  51. [53]

    Khan, Ayaan. ”Federated Learning for Cross-Institutional Genomic Data Analysis in Rare Disease Prediction.” Robotics, Autonomous, Machine Learning, and Artificial intelligence Journal (RAMLAIJ) 2.3 (2023): 16-24

    2023

  52. [54]

    Federated Deep Latent Factor Model for Privacy-Preserving Recommendation

    Gao J, Wu D, Chen J, Zhou M, Luo X. Federated Deep Latent Factor Model for Privacy-Preserving Recommendation. In2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC) 2025 Oct 5 (pp. 1689-1694). IEEE

    2025

  53. [55]

    Serrano, Andr ´e Luiz Marques, et al. ”FedIHRAS: A Privacy-Preserving Federated Learning Framework for Multi-Institutional Collaborative Radiological Analysis with Integrated Explainability and Automated Clinical Reporting.”Biomedicines14.3 (2026): 713

    2026

  54. [56]

    and Luo, X., 2025

    Hu, Q., Wu, H. and Luo, X., 2025. A Comprehensive Review of Parallel Optimization Algorithms for High-Dimensional and Incomplete Matrix Factorization. IEEE/CAA Journal of Automatica Sinica, 12(12), pp.2399-2426

    2025

  55. [57]

    and Luo, X., 2025

    Ma, Q., Wu, D. and Luo, X., 2025. A Review of Deep Learning-Based Power Load Forecasting Methods. International Journal of Network Dynamics and Intelligence, 4(4), p.100027

    2025

  56. [58]

    and Wang, Z., 2025

    Chen, J., Luo, X., Yuan, Y . and Wang, Z., 2025. Enhancing graph convolutional networks with an efficient k-hop neighborhood approach. Information Fusion, 124, p.103297

    2025

  57. [59]

    Multi-Scale Collaborative Distillation Graph Neural Networks for Session-Based Recommendation

    Gou J, Cheng Y , Ma B, Du L, Luo X, Yi Z. Multi-Scale Collaborative Distillation Graph Neural Networks for Session-Based Recommendation. IEEE Transactions on Services Computing. 2025 Nov 25

    2025

  58. [60]

    Ncsac: Effective neural community search via attribute-augmented conductance

    Lin L, Li Q, Qiao M, Wang Z, Zhao J, Li RH, Luo X, Jia T. Ncsac: Effective neural community search via attribute-augmented conductance. IEEE Transactions on Knowledge and Data Engineering. 2025 Nov 7;38(2):1221-35

    2025

  59. [61]

    A scalable multichannel sentiment analysis model with enhanced semantic understanding and redundancy reduction

    Liu J, Li X, Lin M, Luo X. A scalable multichannel sentiment analysis model with enhanced semantic understanding and redundancy reduction. IEEE Transactions on Computational Social Systems. 2025 Nov 6

    2025

  60. [62]

    Neural nonnegative latent factorization of tensors model with acceleration and unconstraint

    Li W, Lin M, Xu X, Lin L, Xu Z, Luo X. Neural nonnegative latent factorization of tensors model with acceleration and unconstraint. IEEE Transactions on Systems, Man, and Cybernetics: Systems. 2025 Oct 30

    2025

  61. [63]

    An intelligent optimization-based residual negative magnitude shaping scheme for vibration control

    Yang W, Li S, Luo X. An intelligent optimization-based residual negative magnitude shaping scheme for vibration control. IEEE Transactions on Industrial Electronics. 2025 Oct 24

    2025

  62. [64]

    Dynamic stochastic reorientation particle swarm optimization for adaptive latent factor analysis in high-dimensional sparse matrices

    Lyu C, Ma Z, Luo X, Shi Y . Dynamic stochastic reorientation particle swarm optimization for adaptive latent factor analysis in high-dimensional sparse matrices. IEEE Transactions on Knowledge and Data Engineering. 2025 Oct 14

    2025

  63. [65]

    Learning accurate representation to nonstandard tensors via a mode-aware tucker network

    Wu H, Wang Q, Luo X, Wang Z. Learning accurate representation to nonstandard tensors via a mode-aware tucker network. IEEE Transactions on Knowledge and Data Engineering. 2025 Oct 3

    2025

  64. [66]

    A convolution bias-incorporated nonnegative latent factorization of tensors model for accurate representation learning to dynamic directed graphs

    Wang Q, Wu H, Luo X. A convolution bias-incorporated nonnegative latent factorization of tensors model for accurate representation learning to dynamic directed graphs. IEEE Transactions on Systems, Man, and Cybernetics: Systems. 2025 Sep 26

    2025

  65. [67]

    Knowledge-driven multiple instance learning with hierarchical cluster-incorporated aware filtering for larynx pathological grading

    Li C, Huang P, Qin J, Luo X. Knowledge-driven multiple instance learning with hierarchical cluster-incorporated aware filtering for larynx pathological grading. IEEE Journal of Biomedical and Health Informatics. 2025 Sep 15

    2025

  66. [68]

    A proximal-admm-incorporated nonnegative latent-factorization-of-tensors model for representing dynamic cryptocurrency transaction network

    Liao X, Wu H, He T, Luo X. A proximal-admm-incorporated nonnegative latent-factorization-of-tensors model for representing dynamic cryptocurrency transaction network. IEEE Transactions on Systems, Man, and Cybernetics: Systems. 2025 Sep 5

    2025

  67. [69]

    Searching for an Accurate Robot Calibration via Improved Levenberg–Marquardt and Radial Basis Function System

    Li Z, Deng X, Chen T, Yang Y , Chen L, Yang X, Hu Z, Hu L, Hu P, Li S, Luo X. Searching for an Accurate Robot Calibration via Improved Levenberg–Marquardt and Radial Basis Function System. Journal of Field Robotics. 2025 Sep;42(6):2691-700

    2025

  68. [70]

    Discovering spatiotemporal–individual coupled features from nonstandard tensors—a novel dynamic graph mixer approach

    Bi F, He T, Ong YS, Luo X. Discovering spatiotemporal–individual coupled features from nonstandard tensors—a novel dynamic graph mixer approach. IEEE Transactions on Neural Networks and Learning Systems. 2025 Aug 6

    2025

  69. [71]

    A novel tensor causal convolution network model for highly-accurate representation to spatio-temporal data

    Liao X, Wu H, Luo X. A novel tensor causal convolution network model for highly-accurate representation to spatio-temporal data. IEEE Transactions on Automation Science and Engineering. 2025 Aug 4

    2025

  70. [72]

    Sgd-dyg: Self-reliant global dependency apprehending on dynamic graphs

    Han M, Wang L, Yuan Y , Luo X. Sgd-dyg: Self-reliant global dependency apprehending on dynamic graphs. InProceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V . 2 2025 Aug 3 (pp. 802-813)

    2025

  71. [73]

    An adaptive neighborhood-resonated graph convolution network for undirected weighted graph representation

    Chen J, Yuan Y , Luo X, Gao X. An adaptive neighborhood-resonated graph convolution network for undirected weighted graph representation. IEEE Transactions on Neural Networks and Learning Systems. 2025 Jul 22

    2025

  72. [74]

    Auto-encoding neural tucker factorization

    Tang P, Luo X, Woodcock J. Auto-encoding neural tucker factorization. IEEE Transactions on Knowledge and Data Engineering. 2025 Jul 17

    2025

  73. [75]

    Neural networks-incorporated latent factor analysis for high-dimensional and incomplete data

    Lin M, Lin X, Xu X, Xu Z, Luo X. Neural networks-incorporated latent factor analysis for high-dimensional and incomplete data. IEEE Transactions on Systems, Man, and Cybernetics: Systems. 2025 Jul 16

    2025

  74. [76]

    Identifying novel therapeutic targets of natural compounds in traditional Chinese medicine herbs with hypergraph representation learning

    Qiao Y , Hu L, Zhang J, Hu P, Luo X. Identifying novel therapeutic targets of natural compounds in traditional Chinese medicine herbs with hypergraph representation learning. Briefings in Bioinformatics. 2025 Jul;26(4):bbaf399

    2025

  75. [77]

    FMvPCI: a multiview fusion neural network for identifying protein complex via fuzzy clustering

    Yang Y , Hu L, Li G, Li D, Hu P, Luo X. FMvPCI: a multiview fusion neural network for identifying protein complex via fuzzy clustering. IEEE Transactions on Systems, Man, and Cybernetics: Systems. 2025 Jun 30

    2025

  76. [78]

    From data analysis to intelligent maintenance: a survey on visual defect detection in aero-engines

    Wu P, Li H, Luo X, Hu L, Yang R, Zeng N. From data analysis to intelligent maintenance: a survey on visual defect detection in aero-engines. Measurement Science and Technology. 2025 Jun 30;36(6):062001

    2025